Identifying Sequence Headings in a Document

5. The method of claim 4, wherein the list of chain fragments is sorted according to the rank of each chain fragment in the list of chain fragments.

7. The CRM of claim 6, the computer readable program code, when executed by the computer, further comprising functionality for: generating a parsed version of the ED, wherein the parsed version of the ED comprises styling attributes of the plurality of characters in the ED; and determining, based on a uniqueness measure of the styling attributes, a confidence of each candidate heading in the list of candidate headings.

8. The CRM of claim 7, the computer readable program code, when executed by the computer, further comprising functionality for: determining, based on the confidence of each candidate heading in the list of candidate headings, a confidence of each chain fragment in the list of chain fragments; and excluding, based on a predetermined confidence threshold and the confidence of each chain fragment, at least one chain fragment from the list of chain fragments for inferring the sequence of section headings.

9. The CRM of claim 6, wherein generating the list of chain fragments further comprises: traversing backwards in the list of candidate headings to identify a leading candidate heading for each chain fragment in the list of chain fragments; and traversing, from the leading candidate heading, forward in the list of candidate headings to identify remaining candidate headings in said each chain fragment, wherein the leading candidate heading includes a leading sequence character in the rightmost digit of the sequence characters.

10. The CRM of claim 6, wherein the list of chain fragments is sorted according to the rank of each chain fragment in the list of chain fragments.

15. The system of claim 11, wherein the list of chain fragments is sorted according to the rank of each chain fragment in the list of chain fragments.